Portrait studio replays drawings to keep the same image
The Drawing You Watch Is the Portrait You Keep: A Replayable Machine Portrait Studio
Human-Computer InteractionComputers and SocietyGraphics
Summary
Most image models create portraits in one go, so each time you ask, you get a different picture with no record of how it was made. The authors built a portrait studio where you watch a drawing appear over time, and that exact drawing is saved and kept. They made a way to replay the drawing without needing the original image model again, ensuring the portrait you see is the portrait you get. They also fixed a problem in their system where darker skin tones were not preserved as well in earlier versions.
What this means in practice
- •For digital artists: Create and save replayable digital portraits that show the drawing process exactly as it happened for clients.$Commercial implications: Enables commercial apps that offer unique, artistic portrait experiences with guaranteed consistency and replay for customers.
- •For interactive media developers: Build interactive portrait experiences where viewers can watch and keep the exact creative drawing steps without rerunning costly models.
Authors
Vinod Rajpurohit
Abstract
Ask an image model for your portrait and a finished picture arrives: no first line, no second thoughts, no record of how it got there, and a different picture if you ask again. I built a portrait studio that works the other way. A sitter chooses one of eight fictional artists, each written with a city, a medium and a tempo of its own, holds still for 8 to 12 seconds, and watches a drawing of themselves appear over 44 seconds. One still is sent after consent, a hosted image model returns a private study the sitter never sees, and a compiler turns that study into one drawing document. The live drawing, the saved sheet, the vector export and the film all read that document, and a replay makes no model call, so the drawing you watch is the portrait you keep. I describe the compiler in enough detail to rebuild it and say plainly what it is: an authored reconstruction at a compressed speed, not a recorded hand. On 16 generated test studies a sheet holds 8,784 to 16,378 timed contacts, about three quarters of them fixed-grid fills and nearly all shorter than one video frame, and recompiling one study gave byte-identical output four times on one machine. The paper also traces a bug that matters more than any of that. The earlier compiler estimated the paper colour tile by tile, read dark skin as paper, and in all eight hands kept less of a deep-complexioned face than a fair one (13 to 48 percent against 41 to 56). On 80 generated studies the rebuilt engine keeps the complexion difference the study already has (raw retention 89 to 120 percent), so the fairness question has moved upstream, to the study and the hosted model. The two test sitters are generated and differ in more than complexion, and no real-face or perceptual study exists yet. The studio is live at https://everyfaceproject.com.